Cultural Prompting Improves the Empathy and Cultural Responsiveness of GPT-Generated Therapy Responses

• URL: http://arxiv.org/abs/2512.00014v1
• Date: Sun, 19 Oct 2025 02:09:29 GMT
• Title: Cultural Prompting Improves the Empathy and Cultural Responsiveness of GPT-Generated Therapy Responses
• Abstract summary: Large Language Model (LLM)-based conversational agents offer promising solutions for mental health support.<n>This study evaluated the effectiveness of cultural prompting in improving cultural responsiveness and perceived empathy.
• Score: 14.378854402393829
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Model (LLM)-based conversational agents offer promising solutions for mental health support, but lack cultural responsiveness for diverse populations. This study evaluated the effectiveness of cultural prompting in improving cultural responsiveness and perceived empathy of LLM-generated therapeutic responses for Chinese American family caregivers. Using a randomized controlled experiment, we compared GPT-4o and Deepseek-V3 responses with and without cultural prompting. Thirty-six participants evaluated input-response pairs on cultural responsiveness (competence and relevance) and perceived empathy. Results showed that cultural prompting significantly enhanced GPT-4o's performance across all dimensions, with GPT-4o with cultural prompting being the most preferred, while improvements in DeepSeek-V3 responses were not significant. Mediation analysis revealed that cultural prompting improved empathy through improving cultural responsiveness. This study demonstrated that prompt-based techniques can effectively enhance the cultural responsiveness of LLM-generated therapeutic responses, highlighting the importance of cultural responsiveness in delivering empathetic AI-based therapeutic interventions to culturally and linguistically diverse populations.

Related papers

• CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia [72.20656906184539]
  We introduce CultureConverse, a scalable, multilingual simulation and evaluation harness for culturally grounded assistant dialogue.<n>The resulting CultureConverse-DS dataset contains 14,610 benchmark (evaluation) episodes and 274,295 oracle-guided (gold-mode) dialogues.<n>Human annotation experiments suggest that our evaluation framework is a sufficient proxy for human judgment.
  arXiv  Detail & Related papers  (2026-08-28T14:56:46Z)
• An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialogue [0.5449798184075946]
  This study introduces a proof-of-concept framework that integrates cognitive behavioral therapy with the African philosophy of Ubuntu.<n>Key CBT techniques, including behavioral activation and cognitive restructuring, were reinterpreted through Ubuntu principles.<n>Results demonstrate that the model effectively engages in empathetic, context-aware dialogue aligned with both therapeutic and cultural objectives.
  arXiv  Detail & Related papers  (2026-01-11T11:50:18Z)
• Cultural Awareness, Stereotypes and Communication Skills in Intercultural Communication: The Algerian Participants Perspective [0.0]
  This study explores the relationship between cultural awareness, stereotypes, and communication skills among Algerian participants working or studying in multicultural environments.<n>Results revealed that while cultural awareness was generally high, certain stereotypes still influenced the perception of others.<n>Participants with higher cultural awareness demonstrated better communication skills and lower levels of stereotyping.
  arXiv  Detail & Related papers  (2025-11-15T22:09:06Z)
• Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity [44.273123155989715]
  Large language models (LLMs) show promise in offering emotional support and generating empathetic responses for individuals in distress.<n>But their ability to deliver culturally sensitive support remains underexplored due to lack of resources.<n>We introduce CultureCare, the first dataset designed for this task, spanning four cultures and including 1729 distress messages, 1523 cultural signals, and 1041 support strategies with fine-grained emotional and cultural annotations.
  arXiv  Detail & Related papers  (2025-08-11T12:17:58Z)
• MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs [25.128936333806678]
  Large language models exhibit cultural biases and limited cross-cultural understanding capabilities.<n>We propose MCEval, a novel multilingual evaluation framework that employs dynamic cultural question construction.
  arXiv  Detail & Related papers  (2025-07-13T16:24:35Z)
• From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test [50.51344198689069]
  We extend the human-centered word association test (WAT) to assess the alignment of large language models with cross-cultural cognition.<n>To address culture preference, we propose CultureSteer, an innovative approach by embedding cultural-specific semantic associations directly within the model's internal representation space.
  arXiv  Detail & Related papers  (2025-05-24T07:05:10Z)
• Multimodal Cultural Safety: Evaluation Frameworks and Alignment Strategies [58.88053690412802]
  Large vision-language models (LVLMs) are increasingly deployed in globally distributed applications, such as tourism assistants.<n> CROSS is a benchmark designed to assess the cultural safety reasoning capabilities of LVLMs.<n>We evaluate 21 leading LVLMs, including mixture-of-experts models and reasoning models.
  arXiv  Detail & Related papers  (2025-05-20T23:20:38Z)
• CAReDiO: Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization [50.90288681622152]
  Large Language Models (LLMs) more deeply integrate into human life across various regions.<n>Existing approaches develop culturally aligned LLMs through fine-tuning with culture-specific corpora.<n>We introduce CAReDiO, a novel cultural data construction framework.
  arXiv  Detail & Related papers  (2025-04-09T13:40:13Z)
• CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries [63.00147630084146]
  Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding.<n>CultureVerse is a large-scale multimodal benchmark covering 19, 682 cultural concepts, 188 countries/regions, 15 cultural concepts, and 3 question types.<n>We propose CultureVLM, a series of VLMs fine-tuned on our dataset to achieve significant performance improvement in cultural understanding.
  arXiv  Detail & Related papers  (2025-01-02T14:42:37Z)
• CulturePark: Boosting Cross-cultural Understanding in Large Language Models [63.452948673344395]
  This paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. We evaluate these models across three downstream tasks: content moderation, cultural alignment, and cultural education.
  arXiv  Detail & Related papers  (2024-05-24T01:49:02Z)
• Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study [9.919972416590124]
  ChatGPT has garnered widespread recognition for its exceptional ability to generate human-like responses in dialogue. We investigate the underlying cultural background of ChatGPT by analyzing its responses to questions designed to quantify human cultural differences.
  arXiv  Detail & Related papers  (2023-03-30T15:43:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.